lec03_features

lec03_features - CS6670:ComputerVision NoahSnavely

Info iconThis preview shows pages 1–25. Sign up to view the full content.

View Full Document Right Arrow Icon
Lecture 3: Feature detection and matching CS6670: Computer Vision Noah Snavely
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Administrivia New location: please sit in the front rows Assignment 1 (feature detection and matching) will be released right after class, due Thursday, September 24 by 11:59pm More details at the end of lecture
Background image of page 2
Reading Szeliski: 4.1
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Why do we flip the kernel? Convolution is commutative Cross correlation is noncommutative
Background image of page 4
Feature extraction: Corners and blobs
Background image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Motivation: Automatic panoramas Credit: Matt Brown
Background image of page 6
http://research.microsoft.com/en us/um/redmond/groups/ivm/HDView/HDGigapixel.htm HD View Also see GigaPan: http://gigapan.org/ Motivation: Automatic panoramas
Background image of page 7

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Why extract features? Motivation: panorama stitching We have two images–how do we combine them?
Background image of page 8
Why extract features? Motivation: panorama stitching We have two images–how do we combine them? Step 1: extract features Step 2: match features
Background image of page 9

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Why extract features? Motivation: panorama stitching We have two images–how do we combine them? Step 1: extract features Step 2: match features Step 3: align images
Background image of page 10
Image matching by Diva Sian by swashford
Background image of page 11

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Harder case by Diva Sian by scgbt
Background image of page 12
Harder still? NASA Mars Rover images
Background image of page 13

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
NASA Mars Rover images with SIFT feature matches Answer below (look for tiny colored squares…)
Background image of page 14
Feature Matching
Background image of page 15

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Feature Matching
Background image of page 16
Invariant local features Find features that are invariant to transformations geometric invariance: translation, rotation, scale photometric invariance: brightness, exposure, … Feature Descriptors
Background image of page 17

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Advantages of local features Locality features are local, so robust to occlusion and clutter Quantity hundreds or thousands in a single image Distinctiveness: can differentiate a large database of objects Efficiency real time performance achievable
Background image of page 18
More motivation… Feature points are used for: Image alignment (e.g., mosaics) 3D reconstruction Motion tracking Object recognition Indexing and database retrieval Robot navigation … other
Background image of page 19

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Snoop demo What makes a good feature?
Background image of page 20
Want uniqueness Look for image regions that are unusual Lead to unambiguous matches in other images How to define “unusual”?
Background image of page 21

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Local measures of uniqueness Suppose we only consider a small window of pixels What defines whether a feature is a good or bad candidate? Credit: S. Seitz, D. Frolova, D. Simakov
Background image of page 22
Local measure of feature uniqueness “flat” region: no change in all directions “edge” : no change along the edge direction “corner” : significant change in all directions How does the window change when you shift it? Shifting the window in any direction causes a big change Credit: S. Seitz, D. Frolova, D. Simakov
Background image of page 23

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Consider shifting the window W by ( u,v ) how do the pixels in W change? compare each pixel before and after by
Background image of page 24
Image of page 25
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 09/27/2010 for the course CS 667 at Cornell.

Page1 / 95

lec03_features - CS6670:ComputerVision NoahSnavely

This preview shows document pages 1 - 25. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online